Xlsx

© 2025 Anthropic, PBC. All rights reserved.

LICENSE: Use of these materials (including all code, prompts, assets, files,
and other components of this Skill) is governed by your agreement with
Anthropic regarding use of Anthropic's services. If no separate agreement
exists, use is governed by Anthropic's Consumer Terms of Service or
Commercial Terms of Service, as applicable:
https://www.anthropic.com/legal/consumer-terms
https://www.anthropic.com/legal/commercial-terms
Your applicable agreement is referred to as the "Agreement." "Services" are
as defined in the Agreement.

ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
contrary, users may not:

- Extract these materials from the Services or retain copies of these
  materials outside the Services
- Reproduce or copy these materials, except for temporary copies created
  automatically during authorized use of the Services
- Create derivative works based on these materials
- Distribute, sublicense, or transfer these materials to any third party
- Make, offer to sell, sell, or import any inventions embodied in these
  materials
- Reverse engineer, decompile, or disassemble these materials

The receipt, viewing, or possession of these materials does not convey or
imply any license or right beyond those expressly granted above.

Anthropic retains all right, title, and interest in these materials,
including all copyrights, patents, and other intellectual property rights.


"""Merge adjacent runs with identical formatting in DOCX.

Merges adjacent <w:r> elements that have identical <w:rPr> properties.
Works on runs in paragraphs and inside tracked changes (<w:ins>, <w:del>).

Also:
- Removes rsid attributes from runs (revision metadata that doesn't affect rendering)
- Removes proofErr elements (spell/grammar markers that block merging)
"""

from pathlib import Path

import defusedxml.minidom


def merge_runs(input_dir: str) -> tuple[int, str]:
    doc_xml = Path(input_dir) / "word" / "document.xml"

    if not doc_xml.exists():
        return 0, f"Error: {doc_xml} not found"

    try:
        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
        root = dom.documentElement

        _remove_elements(root, "proofErr")
        _strip_run_rsid_attrs(root)

        containers = {run.parentNode for run in _find_elements(root, "r")}

        merge_count = 0
        for container in containers:
            merge_count += _merge_runs_in(container)

        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
        return merge_count, f"Merged {merge_count} runs"

    except Exception as e:
        return 0, f"Error: {e}"




def _find_elements(root, tag: str) -> list:
    results = []

    def traverse(node):
        if node.nodeType == node.ELEMENT_NODE:
            name = node.localName or node.tagName
            if name == tag or name.endswith(f":{tag}"):
                results.append(node)
            for child in node.childNodes:
                traverse(child)

    traverse(root)
    return results


def _get_child(parent, tag: str):
    for child in parent.childNodes:
        if child.nodeType == child.ELEMENT_NODE:
            name = child.localName or child.tagName
            if name == tag or name.endswith(f":{tag}"):
                return child
    return None


def _get_children(parent, tag: str) -> list:
    results = []
    for child in parent.childNodes:
        if child.nodeType == child.ELEMENT_NODE:
            name = child.localName or child.tagName
            if name == tag or name.endswith(f":{tag}"):
                results.append(child)
    return results


def _is_adjacent(elem1, elem2) -> bool:
    node = elem1.nextSibling
    while node:
        if node == elem2:
            return True
        if node.nodeType == node.ELEMENT_NODE:
            return False
        if node.nodeType == node.TEXT_NODE and node.data.strip():
            return False
        node = node.nextSibling
    return False




def _remove_